Clinical evaluation of atlas-based auto-segmentation in breast and nodal radiotherapy.

OBJECTIVES: Accurate contouring of anatomical structures allows for high-precision radiotherapy planning, targeting the dose at treatment volumes and avoiding organs at risk. Manual contouring is time-consuming with significant user variability, whereas auto-segmentation (AS) has proven efficiency benefits but requires editing before treatment planning. This study investigated whether atlas-based AS (ABAS) accuracy improves with template atlas group size and character-specific atlas and test case selection. METHODS AND MATERIALS: One clinician retrospectively contoured the breast, nodes, lung, heart, and brachial plexus on 100 CT scans, adhering to peer-reviewed guidelines. Atlases were clustered in group sizes, treatment positions, chest wall separations, and ASs created with Mirada software. The similarity of ASs compared to reference contours was described by the Jaccard similarity coefficient (JSC) and centroid distance variance (CDV). RESULTS: Across group sizes, for all structures combined, the mean JSC was 0.6 (SD 0.3, p = .999). Across atlas-specific groups, 0.6 (SD 0.3, p = 1.000). The correlation between JSC and structure volume was weak in both scenarios (adjusted R2-0.007 and 0.185).Mean CDV was similar across groups but varied up to 1.2 cm for specific structures. CONCLUSIONS: Character-specific atlas groups and test case selection did not improve accuracy outcomes. High-quality ASs were obtained from groups containing as few as ten atlases, subsequently simplifying the application of ABAS. CDV measures indicating auto-segmentation variations on the x, y, and z axes can be utilised to decide on the clinical relevance of variations and reduce AS editing. ADVANCES IN KNOWLEDGE: High-quality ABASs can be obtained from as few as ten template atlases.Atlas and test case selection do not improve AS accuracy.Unlike well-known quantitative similarity indices, volume displacement metrics provide information on the location of segmentation variations, helping assessment of the clinical relevance of variations and reducing clinician editing. Volume displacement metrics combined with the qualitative measure of clinician assessment could reduce user variability.

A dosimetric study to improve the quality of nodal radiotherapy in breast cancer.

OBJECTIVES: Field-based planning for regional nodal breast radiotherapy (RT) used to be standard practice. This study evaluated a field-based posterior axillary boost (PAB) and two forward-planned intensity-modulated RT (IMRT) techniques, aiming to replace the first. METHODS: Supraclavicular and axillary nodes, humeral head, brachial plexus, thyroid, and oesophagus were retrospectively delineated on 12 CT scans. Three plans, prescribed to 40.05 Gy, were produced for each patient. Breast plans consisted of field-in-field IMRT tangential fields in all three techniques. Nodal plans consisted of a field-based PAB (anterior and posterior boost beam), and 2 forward-planned techniques: simple IMRT 1 (anterior and posterior beam with limited segments), and a more advanced IMRT 2 technique (anterior and fully modulated posterior beam). RESULTS: The nodal V90% was similar between IMRT 1: mean 99.5% (SD 1.0) and IMRT 2: 99.4% (SD 0.5). Both demonstrated significantly improved results (p = 0.0001 and 0.005, respectively) compared to the field-based PAB technique. IMRT 2 lung V12Gy and humeral head V10Gy were significantly lower (p = 0.002, 0.0001, respectively) than the field-based PAB technique. IMRT 1 exhibited significantly lower brachial plexus Dmax and humeral head V5, 10, and 15Gy doses (p = 0.007, 0.013, 0.007 and 0.007, respectively) compared to the field-based PAB technique. The oesophagus and thyroid dose difference between methods was insignificant. CONCLUSIONS: Both IMRT techniques achieved the dose coverage requirements and reduced normal tissue exposure, decreasing the risk of radiation side effects. Despite the increased cost of IMRT, compared to non-IMRT techniques 1, both IMRT techniques are suitable for supraclavicular and axillary nodal RT. ADVANCES IN KNOWLEDGE: Forward-planned IMRT already resulted in significant dose reduction to organs at risk and improved planning target volume coverage.1 This new, simplified forward-planned IMRT one technique has not been published in this context and is easy to implement in routine clinical practice.